Introduction

tl;dr: created this to test out what I've learned about advanced LoRA making settings. It worked, so will write an article about advanced LoRA testing soon.

Candy Cobra is a very old OC that I liked in the past, but doesn't seem to have much pictures. The OC nor the owner is active anymore from what I've seen.

Initially I created this model on Pony way back when I was first starting out as a LoRA maker. However the generations were subpar, and that's because it was only trained with 7 images. I decided to unpublish it after awhile as soon as I was publishing my current LoRAs. (In my LoRA making article, I did say having 30-50 images is ideal. I still stand by that!)

Anyway.. decided to revisit this again nearly 10 months later today, especially after learning more about advanced LoRA settings. I decided to publish it again one more time now but using illustrious this time.

After initial testing, I can say I'm actually rather satisfied with the results since it generated way better even with the same training data set of 7 pictures.

It works well even when used with other LoRAs, but I haven't tested it to a point where it might break yet with a lot of LoRAs.

So far, the results were quite good and I didn't need to put much effort into getting what I wanted with the pictures you see above.

Quite sadly after publishing, I lost my old pony LoRA as I didn't save it and apparently CivitAI deletes it if you store it too long in draft, so it's gone at the moment so I can't publish it to show the 'subparness' of the LoRA I made long ago.

But in any case, enjoy the new and updated one! (And expect an article on advanced LoRA making soon where I'll delve into the settings and more!)

Using This LoRA and want to support me? Use the 'add post' in the gallery below - This gives me a lot of blue buzz to train more LoRAs!

---

Illustrious (V1)

It should be able to generate:

• With weightage about 0.8 to 1.0 for best results.

• Anthro (Put "Anthro" trigger words accordingly)

• SFW and NSFW

• Female only (Futa should be fine)

Prompts

Trigger Words: Candy cobra

Additional prompts: snake, anthro snake, purple scales, pink underbelly, snake hood, snake hood markings, striped scales, tail, red eyes, red lipstick, eyelashes, heart shape on chest, anthro, 1girl, red nipples

Notes

• Model is trained on the base Illustrious Model.

• This was made as a test to apply what i've learned about LoRA making. So far, it meets my 'average' requirement of generating at least 80% correctly with the right prompts.

• This LoRA was created with only 7 pictures, so expect not as high quality as my rest. I usually advocate a lot more (30 - 50) as I stated in my LoRA making article.

• LoRA can generate most of her features quite accurately, except at times with certain poses. Especially her heart shape on chest. Use '((heart shape on chest))' with higher weightage if needed.

---

Want to support me without Tipping? Here's how:

1. Liking my posts, collecting my images or collecting my models all generate buzz for me.

2. Generate more pictures of my models. I get a base commission from anyone who generates using my model, even without the tip.

3. Leave a like on my model. This helps me with the algorithm in reaching more people

4. Leave a review. I take all feedback very seriously, good or bad.

5. Consider using the 'add post' under gallery... if you are posting pictures of just my LoRA. The images will also still appear on your profile but this will give me A LOT of buzz, while you can also complete your daily post quest.

   

   Thank you very much!